OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time Optimization

Watermarking diffusion-generated images is crucial for copyright protection and user tracking. However, current diffusion watermarking methods face significant limitations: zero-bit watermarking systems lack the capacity for large-scale user tracking, while multi-bit methods are highly sensitive to certain image transformations or generative attacks, resulting in a lack of comprehensive robustness. In this paper, we propose OptMark, an optimization-based approach that embeds a robust multi-bit watermark into the intermediate latents of the diffusion denoising process. OptMark strategically inserts a structural watermark early to resist generative attacks and a detail watermark late to withstand image transformations, with tailored regularization terms to preserve image quality and ensure imperceptibility. To address the challenge of memory consumption growing linearly with the number of denoising steps during optimization, OptMark incorporates adjoint gradient methods, reducing memory usage from O(N) to O(1). Experimental results demonstrate that OptMark achieves invisible multi-bit watermarking while ensuring robust resilience against valuemetric transformations, geometric transformations, editing, and regeneration attacks.

Key Contributions

• Dual-phase watermark injection: structural watermark inserted early in denoising (resists generative/regeneration attacks) and detail watermark inserted late (resists image transformations), with tailored regularization for imperceptibility
• Adjoint gradient optimization that reduces memory footprint from O(N) to O(1) relative to denoising steps, enabling practical inference-time optimization
• Achieves ~0.983 bit accuracy and ~0.972 TPR across valuemetric, geometric, editing, and regeneration attacks while maintaining near-baseline image quality (ΔFID=3.069)

🛡️ Threat Analysis

Details

Similar Papers